Instructions to use WitneyWW/acts-sensoronly-ablation with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Cosmos
How to use WitneyWW/acts-sensoronly-ablation with Cosmos:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Download checkpoints/vae/train_config.json from WitneyWW/acts-sensoronly-ablation: direct link, hf CLI and curl.
- Browser
- Download file 763 Bytes
-
https://huggingface.co/WitneyWW/acts-sensoronly-ablation/resolve/main/checkpoints/vae/train_config.json
- Command line
-
hf download hf://WitneyWW/acts-sensoronly-ablation/checkpoints/vae/train_config.json
-
curl -L -o train_config.json https://huggingface.co/WitneyWW/acts-sensoronly-ablation/resolve/main/checkpoints/vae/train_config.json
763 Bytes
| { | |
| "vae_pth": "/group2/ct/weihanx/Wan-AI/Wan2.2-TI2V-5B/Wan2.2_VAE.pth", | |
| "csv": "/group2/ct/weihanx/world_model/data_preprocessing/freetacman_tactile_shuffled_filtered.csv", | |
| "out": "./lora_out_refflow", | |
| "num_frames": 17, | |
| "height": 256, | |
| "width": 256, | |
| "val_size": 64, | |
| "num_workers": 8, | |
| "fps": 6.0, | |
| "src_fps": 30.0, | |
| "lora_r": 32, | |
| "lora_alpha": 32.0, | |
| "lora_dropout": 0.0, | |
| "lora_targets": "all", | |
| "batch_size": 1, | |
| "grad_accum": 4, | |
| "lr": 0.0001, | |
| "weight_decay": 0.0, | |
| "steps": 4000, | |
| "warmup": 100, | |
| "grad_clip": 1.0, | |
| "lpips_weight": 0.1, | |
| "edge_weight": 1.0, | |
| "flow_weight": 1.0, | |
| "flow_floor": 1.5, | |
| "flow_suffix": "_refflow.npz", | |
| "log_every": 20, | |
| "val_every": 500, | |
| "save_every": 1000, | |
| "dtype": "bf16", | |
| "seed": 0 | |
| } |